ClawHub
Back to skill

Security audit

Cfo Advisor

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed CFO-advisory prompt package with some broad routing language, but no hidden execution, persistence, credential use, or data export behavior was found.

Install only if you want CFO-style strategic finance guidance and are comfortable with the agent reading company-context.md for relevant finance tasks. Treat outputs as planning support, not professional financial, legal, tax, or investment advice; verify assumptions and numbers before using them for decisions.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation description uses broad trigger language such as 'use when' across many common finance terms, which can cause the skill to activate in situations where a narrower or different skill would be more appropriate. In an agentic system, overly broad routing increases the chance of mis-scoped behavior, unnecessary access to sensitive business context, and incorrect high-stakes financial advice being surfaced under weak relevance checks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The keyword list is extremely broad and contains many common business terms that may appear in unrelated contexts, making it unsafe as a trigger surface on its own. In this skill's context, that broadness is more dangerous because the skill also instructs reading company-context.md and supports strategic financial outputs, so accidental invocation could expose sensitive internal context or steer decisions based on the wrong specialist lens.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

L019 explicitly states the skill is not a financial analyst skill, but the rest of the file describes concrete analyst-style functions such as runway modeling, per-cohort LTV/CAC analysis, budget building, and board financial package preparation. This is an active contradiction in the skill's own documentation about what the skill is intended to do.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.